Onboarding / beta

Get started

Five minutes, start to finish. Pick what you want to do.

  1. Sign in

    Loading...

  2. Create an API key

    New keys can take about 5 seconds to start working.

  3. Pick your tool

    Put your key in the environment, then save this as opencode.json in your project (or ~/.config/opencode/opencode.json).

    Shell
    opencode.json

    Then run opencode and pick tessovix/tessovix-mini with /models.

  4. Send your first request

    Use your tool, or run this from a terminal. We will notice the request on our side.

    Shell

  5. Verified

    Waiting for your first request...

  6. Install the node

    Linux (x86_64, aarch64) or macOS (arm64). Run this in a terminal.

    Install
    What this does
    • Downloads tessovix-node for your platform from beaver.tessovix.com and checks its SHA-256. It stops if the checksum does not match.
    • Installs the binary to ~/.local/bin.
    • Saves your key and the gateway address in ~/.config/tessovix/node.env, readable only by you.
    • On Linux with systemd, creates and starts a tessovix-node user service.
    • Does not install an inference engine or models. That is the next part.
    Manual alternative

    Download tessovix-node-<target>.tar.gz and its .sha256 from https://beaver.tessovix.com/dl/, compare the checksum, and unpack tessovix-node into ~/.local/bin. Then run it with these variables set:

    Shell

    Start an engine

    The node serves requests from a local llama.cpp server on 127.0.0.1:8081. Use the model file and alias from your beta invitation.

    Get a CUDA, Metal or Vulkan build of llama.cpp, then:

    Shell
    llama-server -m ~/models/MODEL.gguf --alias ALIAS \
      --jinja -ngl 99 -c 16384 \
      --host 127.0.0.1 --port 8081
  7. Wait for your node

    Waiting for a node to connect...

  8. Done

    Your node is online and verified. It now serves requests.

    How earning works Open the dashboard